SPEECH AND SPEAKER RECOGNITION SYSTEM USING ARTIFICIAL NEURAL NETWORKS AND HIDDEN MARKOV MODEL

    Speech is the most efficient way to train a machine or communicate with a machine. This work focuses on the objective to recognize the word or the phrase spoken by humans, keywords at high speed. But as speech is a biometric property and biometric property of humans is difficult to recognize. Hence the human leaded learning processes for machines are not so successful. Although the recognition of speech using pattern mapping algorithms is successful, especially continuous learning algorithms like backpropagation algorithm using any combination of feedforward and feedback networks with Gradient searching capabilities. The generation of voice or speech signal is from the vocal muscles, which depends on the physical structure of human and it varies regularly. Moreover, the signal is also affected by the emotions of the speakers. Therefore it’s required to neutralize the signals to derive emotion-free inputs to the detection system, analysis of spectrograms of the speech signal and further mapping of input spectrogram set to output spectrogram set. After the neutralization, the signal is free from emotions and the spectrogram analysis generates the best input sets which can be mapped to the output dataset, which is obtained during training, hence we propose an algorithm to map input spectrum analysis depicted to the machine voice spectrum deprecated for speech recognition. A methodology to identify speaker and detection of speech based on the Hidden Markov Model for security is designed using Matlab. Within the speech signal, analysis of spectrogram, neutralization, extraction of features for recognition, mapping of speech using Artificial Neural networks is presented. In our design, such a method of mapping is realized using backpropagation rules of neural networks.

Reference Paper: Speech and Speaker Recognition System using Artificial Neural Networks and Hidden Markov Model
Author’s Name: Niladri Sekhar Dey, Ramakanta Mohanty and K. L. Chugh
Source: IEEE
Year:2012

Request source code for academic purpose, fill REQUEST FORM or contact +91 7904568456 by WhatsApp or sales@verilogcourseteam.com, fee applicable.

SIMULATION VIDEO DEMO                                                                                                                            




PREVIOUS PAGE|NEXT PAGE